def process_url(self, source, global_opts):
"""Main method for processing urls
This method basically hands over the configuration to YoutubeDL and repeats
the step until every source in the configuration was read
"""
ydl = YoutubeDL()
ydl.add_default_info_extractors()
sourceUrl = source['url']
sourceDescription = source.get("description", "")
self._logsource(
"Processing source: '" + sourceDescription +
"' Url: '" + sourceUrl + "'", source)
# Merge local parameters with global ones
ydl.params = copy.copy(global_opts)
ydl.params.update(source)
prefix = ""
ydl.params['match_filter'] = (
None if 'match_filter' not in ydl.params or ydl.params['match_filter'] is None
else match_filter_func(ydl.params['match_filter']))
# Settings by commute tube over the standard settings, respect if the config sets them differently
if 'format' not in ydl.params and 'format_limit' not in ydl.params:
ydl.params['format'] = "bestvideo+bestaudio/best" if 'format' not in self.config else self.config["format"]
if 'nooverwrites' not in ydl.params:
ydl.params['nooverwrites'] = True
if 'ignoreerrors' not in ydl.params:
ydl.params['ignoreerrors'] = True
if 'download_archive' not in ydl.params:
ydl.params['download_archive'] = self.download_archive
if 'prefix' in ydl.params:
prefix = ydl.params['prefix']
ydl.params['restrictfilenames'] = True
ydl.params['logger'] = self.ydlLog
outtmpl = self.pathToDownloadFolder + "/" + prefix + \
'%(uploader)s-%(title)s.%(ext)s'
if 'outtmpl' not in ydl.params:
ydl.params['outtmpl'] = outtmpl
elif not (ydl.params['outtmpl'].startswith(self.pathToDownloadFolder)):
self._logsource("Prefixing custom set outtmpl with '" + self.pathToDownloadFolder + "/" + prefix + "'", source)
ydl.params['outtmpl'] = self.pathToDownloadFolder + "/" + prefix + \
ydl.params['outtmpl']
if self.debug:
self._logsource(
"All downloads will be simulated since this is debug mode", source)
ydl.params['simulate'] = True
ydl.download([source['url']])
ydl_opts = {
"format": "best",
"logger": log,
"restrictfilenames": True,
"ignoreerrors": True,
"nooverwrites": True,
"writedescription": True,
"writeinfojson": True,
"writesubtitles": True,
"writeautomaticsub": True,
"outtmpl":
"{}/%(extractor)s/%(id)s/%(title)s.%(ext)s".format(download_dir),
"download_archive": "{}/archive.txt".format(download_dir),
}
if args.ignore_livestreams:
ydl_opts["matchfilter"] = match_filter_func("!is_live")
if args.max_downloads:
ydl_opts["max_downloads"] = args.max_downloads
if args.max_filesize:
ydl_opts["max_filesize"] = args.max_filesize
# keep track of domains to block
blocklist = []
if args.block:
blocklist = args.block
# read in existing mapping file to know which urls we can ignorej
seen = set()
mapping_file = os.path.join(download_dir, "mapping.tsv")
if os.path.isfile(mapping_file):
for line in open(mapping_file):
def test_match_filter(self):
class FilterYDL(YDL):
def __init__(self, *args, **kwargs):
super(FilterYDL, self).__init__(*args, **kwargs)
self.params['simulate'] = True
def process_info(self, info_dict):
super(YDL, self).process_info(info_dict)
def _match_entry(self, info_dict, incomplete):
res = super(FilterYDL,
self)._match_entry(info_dict, incomplete)
if res is None:
self.downloaded_info_dicts.append(info_dict)
return res
first = {
'id': '1',
'url': TEST_URL,
'title': 'one',
'extractor': 'TEST',
'duration': 30,
'filesize': 10 * 1024,
'playlist_id': '42',
}
second = {
'id': '2',
'url': TEST_URL,
'title': 'two',
'extractor': 'TEST',
'duration': 10,
'description': 'foo',
'filesize': 5 * 1024,
'playlist_id': '43',
}
videos = [first, second]
def get_videos(filter_=None):
ydl = FilterYDL({'match_filter': filter_})
for v in videos:
ydl.process_ie_result(v, download=True)
return [v['id'] for v in ydl.downloaded_info_dicts]
res = get_videos()
self.assertEqual(res, ['1', '2'])
def f(v):
if v['id'] == '1':
return None
else:
return 'Video id is not 1'
res = get_videos(f)
self.assertEqual(res, ['1'])
f = match_filter_func('duration < 30')
res = get_videos(f)
self.assertEqual(res, ['2'])
f = match_filter_func('description = foo')
res = get_videos(f)
self.assertEqual(res, ['2'])
f = match_filter_func('description =? foo')
res = get_videos(f)
self.assertEqual(res, ['1', '2'])
f = match_filter_func('filesize > 5KiB')
res = get_videos(f)
self.assertEqual(res, ['1'])
f = match_filter_func('playlist_id = 42')
res = get_videos(f)
self.assertEqual(res, ['1'])
def ytdlProcess(config, conn):
global ErrorList, SQLrows2Add
sep = SEPARATOR
cols = config['MetaColumns']
dlBase = config['DLbase']
dlArch = dlBase + config['DLarch']
dlElog = dlBase + config['DLeLog']
dlOpts = config['DLOpts']
grupeList = config['Grupes']
total = 0
failures = 0
# NOTE: items missing from metadata will be replaced with "?"
ytdlFileFormat = "/%(id)s" + sep + "%(duration)s"+ sep + ".%(ext)s"
dlOpts['ignoreerrors'] = True # TEMPORARY ?????
#dlOpts['verbose'] = True # Useful for debugging
# Add crucial download options. Some options MUST be added in the DL loop
# dlOpts['force-ipv6'] = True # May not be enabled on host
dlOpts['writeinfojson'] = True
dlOpts['progress_hooks'] = [callback] # Called at least once / video
dlOpts['download_archive'] = dlArch # Facilitates updates w/o dupes
dlOpts['restrictfilenames'] = True # Required format for DLd files
eLog = open(dlElog, mode='a+') # Error log file for all grupes
with youtube_dl.YoutubeDL(dlOpts) as ydl:
for grupe in grupeList:
if not grupeList[grupe]['Active']: continue # Skip this grupe
SQLrows2Add = [] # Empty the list of downloads
ErrorList = [] # Empty the list of errors
print("\nBEGIN " + grupe) # Marks start of group in log
if not os.path.isdir(dlBase + grupe): # If it doesn't exist
os.mkdir(dlBase + grupe) # create folder 4 grupe
# Add qualifier for minimum video duration (in seconds)
dur = grupeList[grupe]['Duration']
if dur != None and dur > 0:
dur = "duration > %d" % dur
ydl.params['match_filter'] = utils.match_filter_func(dur)
elif 'match_filter' in ydl.params.keys():
del ydl.params['match_filter'] # No duration filter
# Add release date range qualifier; either one or both are OK
sd = grupeList[grupe]['Start'] # null or YYYYMMDD format
ed = grupeList[grupe]['End'] # in JSON config file
if sd != None or ed != None:
dr = utils.DateRange(sd, ed) # Dates are inclusive
ydl.params['daterange'] = dr # Always set a date range
elif 'daterange' in ydl.params.keys():
del ydl.params['daterange'] # No date filter
# This stops downloading from playlist after this many videos
stop = grupeList[grupe]['Stop']
if stop != None and stop > 0: ydl.params['playlistend'] = stop
elif 'playlistend' in ydl.params.keys():
del ydl.params['playlistend'] # No playlist limit
# This will change downloaded file folder for each grupe
ydl.params['outtmpl'] = dlBase + grupe + ytdlFileFormat
urls = grupeList[grupe]['urls']
# Don't even try downloading videos we already have in the DB
newUrls = filterUrls(conn, urls)
ydl.download(newUrls) # BEGIN DOWNLOADING!!!
print("YOUTUBE-DL PROCESSING COMPLETE for %s" % grupe)
# Wait for all callback threads to finish
for th in threading.enumerate():
if th.name != "MainThread":
th.join()
# Log errors and print results of this DL grupe
good, fails = processGrupeResults(conn, cols,
len(urls), grupe, eLog)
total += good
failures += fails # Accumulate totals for this run
eLog.close()
return total, failures
def test_match_filter(self):
class FilterYDL(YDL):
def __init__(self, *args, **kwargs):
super(FilterYDL, self).__init__(*args, **kwargs)
self.params['simulate'] = True
def process_info(self, info_dict):
super(YDL, self).process_info(info_dict)
def _match_entry(self, info_dict, incomplete):
res = super(FilterYDL, self)._match_entry(info_dict, incomplete)
if res is None:
self.downloaded_info_dicts.append(info_dict)
return res
first = {
'id': '1',
'url': TEST_URL,
'title': 'one',
'extractor': 'TEST',
'duration': 30,
'filesize': 10 * 1024,
'playlist_id': '42',
'uploader': "變態妍字幕版 太妍 тест",
'creator': "тест ' 123 ' тест--",
}
second = {
'id': '2',
'url': TEST_URL,
'title': 'two',
'extractor': 'TEST',
'duration': 10,
'description': 'foo',
'filesize': 5 * 1024,
'playlist_id': '43',
'uploader': "тест 123",
}
videos = [first, second]
def get_videos(filter_=None):
ydl = FilterYDL({'match_filter': filter_})
for v in videos:
ydl.process_ie_result(v, download=True)
return [v['id'] for v in ydl.downloaded_info_dicts]
res = get_videos()
self.assertEqual(res, ['1', '2'])
def f(v):
if v['id'] == '1':
return None
else:
return 'Video id is not 1'
res = get_videos(f)
self.assertEqual(res, ['1'])
f = match_filter_func('duration < 30')
res = get_videos(f)
self.assertEqual(res, ['2'])
f = match_filter_func('description = foo')
res = get_videos(f)
self.assertEqual(res, ['2'])
f = match_filter_func('description =? foo')
res = get_videos(f)
self.assertEqual(res, ['1', '2'])
f = match_filter_func('filesize > 5KiB')
res = get_videos(f)
self.assertEqual(res, ['1'])
f = match_filter_func('playlist_id = 42')
res = get_videos(f)
self.assertEqual(res, ['1'])
f = match_filter_func('uploader = "變態妍字幕版 太妍 тест"')
res = get_videos(f)
self.assertEqual(res, ['1'])
f = match_filter_func('uploader != "變態妍字幕版 太妍 тест"')
res = get_videos(f)
self.assertEqual(res, ['2'])
f = match_filter_func('creator = "тест \' 123 \' тест--"')
res = get_videos(f)
self.assertEqual(res, ['1'])
f = match_filter_func("creator = 'тест \\' 123 \\' тест--'")
res = get_videos(f)
self.assertEqual(res, ['1'])
f = match_filter_func(r"creator = 'тест \' 123 \' тест--' & duration > 30")
res = get_videos(f)
self.assertEqual(res, [])
def main():
args = parser.parse_args()
# make download directory
download_dir = args.download_dir
if not os.path.isdir(download_dir):
os.mkdir(download_dir)
# setup logger
log_file = "{}/youtubedl.log".format(download_dir)
logging.basicConfig(filename=log_file, level=logging.INFO)
log = logging.getLogger()
# setup youtube_dl config
ydl_opts = {
"format": "best",
"logger": log,
"restrictfilenames": True,
"ignoreerrors": True,
"nooverwrites": True,
"writedescription": True,
"writeinfojson": True,
"writesubtitles": True,
"writeautomaticsub": True,
"outtmpl":
"{}/%(extractor)s/%(id)s/%(title)s.%(ext)s".format(download_dir),
"download_archive": "{}/archive.txt".format(download_dir)
}
if args.ignore_livestreams:
ydl_opts["matchfilter"] = match_filter_func("!is_live")
if args.max_downloads:
ydl_opts['max_downloads'] = args.max_downloads
if args.max_filesize:
ydl_opts['max_filesize'] = args.max_filesize
# keep track of domains to block
blocklist = []
if args.block:
blocklist = args.block
# read in existing mapping file to know which urls we can ignorej
seen = set()
mapping_file = os.path.join(download_dir, 'mapping.tsv')
if os.path.isfile(mapping_file):
for line in open(mapping_file):
url, path = line.split('\t')
log.info('found %s in %s', url, mapping_file)
seen.add(url)
# loop through the tweets
results = open(mapping_file, 'a')
for line in fileinput.input(args.files):
tweet = json.loads(line)
log.info('analyzing %s', tweet['id_str'])
for e in tweet['entities']['urls']:
url = e.get('unshortened_url') or e['expanded_url']
# see if we can skip this one
if not url:
continue
if url in seen:
log.info('already processed %s', url)
continue
seen.add(url)
# check for blocks
uri = urlparse(url)
if uri.netloc in blocklist:
logging.warn("%s in block list", url)
continue
# set up a multiprocessing queue to manage the download with a timeout
log.info('processing %s', url)
q = mp.Queue()
p = mp.Process(target=download, args=(url, q, ydl_opts, log))
p.start()
started = datetime.now()
while True:
# if we've exceeded the timeout terminate the process
if args.timeout and datetime.now() - started > timedelta(
seconds=args.timeout):
log.warning('reached timeout %s', args.timeout)
p.terminate()
break
# if the process is done we can stop
elif not p.is_alive():
break
# otherwise sleep and the check again
time.sleep(1)
# if the queue was empty there either wasn't a download or it timed out
if q.empty():
filename = ''
else:
filename = q.get()
p.join()
# write the result to the mapping file
results.write("{}\t{}\n".format(url, filename))
def _real_main(myurl,argv=None):
# Compatibility fixes for Windows
if sys.platform == 'win32':
# https://github.com/rg3/youtube-dl/issues/820
codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
workaround_optparse_bug9161()
setproctitle('youtube-dl')
parser, opts, args = parseOpts(argv)
# Set user agent
if opts.user_agent is not None:
std_headers['User-Agent'] = opts.user_agent
# Set referer
if opts.referer is not None:
std_headers['Referer'] = opts.referer
# Custom HTTP headers
if opts.headers is not None:
for h in opts.headers:
if ':' not in h:
parser.error('wrong header formatting, it should be key:value, not "%s"' % h)
key, value = h.split(':', 1)
if opts.verbose:
write_string('[debug] Adding header from command line option %s:%s\n' % (key, value))
std_headers[key] = value
# Dump user agent
if opts.dump_user_agent:
write_string(std_headers['User-Agent'] + '\n', out=sys.stdout)
sys.exit(0)
# Batch file verification
batch_urls = []
if opts.batchfile is not None:
try:
if opts.batchfile == '-':
batchfd = sys.stdin
else:
batchfd = io.open(
expand_path(opts.batchfile),
'r', encoding='utf-8', errors='ignore')
batch_urls = read_batch_urls(batchfd)
if opts.verbose:
write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
except IOError:
sys.exit('ERROR: batch file could not be read')
all_urls = batch_urls + [url.strip() for url in args] # batch_urls are already striped in read_batch_urls
_enc = preferredencoding()
all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
if opts.list_extractors:
for ie in list_extractors(opts.age_limit):
write_string(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else '') + '\n', out=sys.stdout)
matchedUrls = [url for url in all_urls if ie.suitable(url)]
for mu in matchedUrls:
write_string(' ' + mu + '\n', out=sys.stdout)
sys.exit(0)
if opts.list_extractor_descriptions:
for ie in list_extractors(opts.age_limit):
if not ie._WORKING:
continue
desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
if desc is False:
continue
if hasattr(ie, 'SEARCH_KEY'):
_SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
_COUNTS = ('', '5', '10', 'all')
desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
write_string(desc + '\n', out=sys.stdout)
sys.exit(0)
if opts.ap_list_mso:
table = [[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()]
write_string('Supported TV Providers:\n' + render_table(['mso', 'mso name'], table) + '\n', out=sys.stdout)
sys.exit(0)
if opts.usenetrc and (opts.username is not None or opts.password is not None):
parser.error('using .netrc conflicts with giving username/password')
if opts.password is not None and opts.username is None:
parser.error('account username missing\n')
if opts.ap_password is not None and opts.ap_username is None:
parser.error('TV Provider account username missing\n')
if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
parser.error('using output template conflicts with using title, video ID or auto number')
if opts.autonumber_size is not None:
if opts.autonumber_size <= 0:
parser.error('auto number size must be positive')
if opts.autonumber_start is not None:
if opts.autonumber_start < 0:
parser.error('auto number start must be positive or 0')
if opts.usetitle and opts.useid:
parser.error('using title conflicts with using video ID')
if opts.username is not None and opts.password is None:
opts.password = compat_getpass('Type account password and press [Return]: ')
if opts.ap_username is not None and opts.ap_password is None:
opts.ap_password = compat_getpass('Type TV provider account password and press [Return]: ')
if opts.ratelimit is not None:
numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
if numeric_limit is None:
parser.error('invalid rate limit specified')
opts.ratelimit = numeric_limit
if opts.min_filesize is not None:
numeric_limit = FileDownloader.parse_bytes(opts.min_filesize)
if numeric_limit is None:
parser.error('invalid min_filesize specified')
opts.min_filesize = numeric_limit
if opts.max_filesize is not None:
numeric_limit = FileDownloader.parse_bytes(opts.max_filesize)
if numeric_limit is None:
parser.error('invalid max_filesize specified')
opts.max_filesize = numeric_limit
if opts.sleep_interval is not None:
if opts.sleep_interval < 0:
parser.error('sleep interval must be positive or 0')
if opts.max_sleep_interval is not None:
if opts.max_sleep_interval < 0:
parser.error('max sleep interval must be positive or 0')
if opts.max_sleep_interval < opts.sleep_interval:
parser.error('max sleep interval must be greater than or equal to min sleep interval')
else:
opts.max_sleep_interval = opts.sleep_interval
if opts.ap_mso and opts.ap_mso not in MSO_INFO:
parser.error('Unsupported TV Provider, use --ap-list-mso to get a list of supported TV Providers')
def parse_retries(retries):
if retries in ('inf', 'infinite'):
parsed_retries = float('inf')
else:
try:
parsed_retries = int(retries)
except (TypeError, ValueError):
parser.error('invalid retry count specified')
return parsed_retries
if opts.retries is not None:
opts.retries = parse_retries(opts.retries)
if opts.fragment_retries is not None:
opts.fragment_retries = parse_retries(opts.fragment_retries)
if opts.buffersize is not None:
numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
if numeric_buffersize is None:
parser.error('invalid buffer size specified')
opts.buffersize = numeric_buffersize
if opts.http_chunk_size is not None:
numeric_chunksize = FileDownloader.parse_bytes(opts.http_chunk_size)
if not numeric_chunksize:
parser.error('invalid http chunk size specified')
opts.http_chunk_size = numeric_chunksize
if opts.playliststart <= 0:
raise ValueError('Playlist start must be positive')
if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
raise ValueError('Playlist end must be greater than playlist start')
if opts.extractaudio:
if opts.audioformat not in ['best', 'aac', 'flac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']:
parser.error('invalid audio format specified')
if opts.audioquality:
opts.audioquality = opts.audioquality.strip('k').strip('K')
if not opts.audioquality.isdigit():
parser.error('invalid audio quality specified')
if opts.recodevideo is not None:
if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv', 'avi']:
parser.error('invalid video recode format specified')
if opts.convertsubtitles is not None:
if opts.convertsubtitles not in ['srt', 'vtt', 'ass', 'lrc']:
parser.error('invalid subtitle format specified')
if opts.date is not None:
date = DateRange.day(opts.date)
else:
date = DateRange(opts.dateafter, opts.datebefore)
# Do not download videos when there are audio-only formats
if opts.extractaudio and not opts.keepvideo and opts.format is None:
opts.format = 'bestaudio/best'
# --all-sub automatically sets --write-sub if --write-auto-sub is not given
# this was the old behaviour if only --all-sub was given.
if opts.allsubtitles and not opts.writeautomaticsub:
opts.writesubtitles = True
outtmpl = ((opts.outtmpl is not None and opts.outtmpl) or
(opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s') or
(opts.format == '-1' and '%(id)s-%(format)s.%(ext)s') or
(opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s') or
(opts.usetitle and '%(title)s-%(id)s.%(ext)s') or
(opts.useid and '%(id)s.%(ext)s') or
(opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s') or
DEFAULT_OUTTMPL)
if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
parser.error('Cannot download a video and extract audio into the same'
' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
' template'.format(outtmpl))
any_getting = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson or opts.dump_single_json
any_printing = opts.print_json
download_archive_fn = expand_path(opts.download_archive) if opts.download_archive is not None else opts.download_archive
# PostProcessors
postprocessors = []
if opts.metafromtitle:
postprocessors.append({
'key': 'MetadataFromTitle',
'titleformat': opts.metafromtitle
})
if opts.extractaudio:
postprocessors.append({
'key': 'FFmpegExtractAudio',
'preferredcodec': opts.audioformat,
'preferredquality': opts.audioquality,
'nopostoverwrites': opts.nopostoverwrites,
})
if opts.recodevideo:
postprocessors.append({
'key': 'FFmpegVideoConvertor',
'preferedformat': opts.recodevideo,
})
if opts.addmetadata:
postprocessors.append({'key': 'FFmpegMetadata'})
if opts.convertsubtitles:
postprocessors.append({
'key': 'FFmpegSubtitlesConvertor',
'format': opts.convertsubtitles,
})
if opts.embedsubtitles:
postprocessors.append({
'key': 'FFmpegEmbedSubtitle',
})
if opts.embedthumbnail:
already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
postprocessors.append({
'key': 'EmbedThumbnail',
'already_have_thumbnail': already_have_thumbnail
})
if not already_have_thumbnail:
opts.writethumbnail = True
if opts.xattrs:
postprocessors.append({'key': 'XAttrMetadata'})
if opts.exec_cmd:
postprocessors.append({
'key': 'ExecAfterDownload',
'exec_cmd': opts.exec_cmd,
})
external_downloader_args = None
if opts.external_downloader_args:
external_downloader_args = compat_shlex_split(opts.external_downloader_args)
postprocessor_args = None
if opts.postprocessor_args:
postprocessor_args = compat_shlex_split(opts.postprocessor_args)
match_filter = (
None if opts.match_filter is None
else match_filter_func(opts.match_filter))
ydl_opts = {
'usenetrc': opts.usenetrc,
'username': opts.username,
'password': opts.password,
'twofactor': opts.twofactor,
'videopassword': opts.videopassword,
'ap_mso': opts.ap_mso,
'ap_username': opts.ap_username,
'ap_password': opts.ap_password,
'quiet': (opts.quiet or any_getting or any_printing),
'no_warnings': opts.no_warnings,
'forceurl': opts.geturl,
'forcetitle': opts.gettitle,
'forceid': opts.getid,
'forcethumbnail': opts.getthumbnail,
'forcedescription': opts.getdescription,
'forceduration': opts.getduration,
'forcefilename': opts.getfilename,
'forceformat': opts.getformat,
'forcejson': opts.dumpjson or opts.print_json,
'dump_single_json': opts.dump_single_json,
'simulate': opts.simulate or any_getting,
'skip_download': opts.skip_download,
'format': opts.format,
'listformats': opts.listformats,
'outtmpl': outtmpl,
'autonumber_size': opts.autonumber_size,
'autonumber_start': opts.autonumber_start,
'restrictfilenames': opts.restrictfilenames,
'ignoreerrors': opts.ignoreerrors,
'force_generic_extractor': opts.force_generic_extractor,
'ratelimit': opts.ratelimit,
'nooverwrites': opts.nooverwrites,
'retries': opts.retries,
'fragment_retries': opts.fragment_retries,
'skip_unavailable_fragments': opts.skip_unavailable_fragments,
'keep_fragments': opts.keep_fragments,
'buffersize': opts.buffersize,
'noresizebuffer': opts.noresizebuffer,
'http_chunk_size': opts.http_chunk_size,
'continuedl': opts.continue_dl,
'noprogress': opts.noprogress,
'progress_with_newline': opts.progress_with_newline,
'playliststart': opts.playliststart,
'playlistend': opts.playlistend,
'playlistreverse': opts.playlist_reverse,
'playlistrandom': opts.playlist_random,
'noplaylist': opts.noplaylist,
'logtostderr': opts.outtmpl == '-',
'consoletitle': opts.consoletitle,
'nopart': opts.nopart,
'updatetime': opts.updatetime,
'writedescription': opts.writedescription,
'writeannotations': opts.writeannotations,
'writeinfojson': opts.writeinfojson,
'writethumbnail': opts.writethumbnail,
'write_all_thumbnails': opts.write_all_thumbnails,
'writesubtitles': opts.writesubtitles,
'writeautomaticsub': opts.writeautomaticsub,
'allsubtitles': opts.allsubtitles,
'listsubtitles': opts.listsubtitles,
'subtitlesformat': opts.subtitlesformat,
'subtitleslangs': opts.subtitleslangs,
'matchtitle': decodeOption(opts.matchtitle),
'rejecttitle': decodeOption(opts.rejecttitle),
'max_downloads': opts.max_downloads,
'prefer_free_formats': opts.prefer_free_formats,
'verbose': opts.verbose,
'dump_intermediate_pages': opts.dump_intermediate_pages,
'write_pages': opts.write_pages,
'test': opts.test,
'keepvideo': opts.keepvideo,
'min_filesize': opts.min_filesize,
'max_filesize': opts.max_filesize,
'min_views': opts.min_views,
'max_views': opts.max_views,
'daterange': date,
'cachedir': opts.cachedir,
'youtube_print_sig_code': opts.youtube_print_sig_code,
'age_limit': opts.age_limit,
'download_archive': download_archive_fn,
'cookiefile': opts.cookiefile,
'nocheckcertificate': opts.no_check_certificate,
'prefer_insecure': opts.prefer_insecure,
'proxy': opts.proxy,
'socket_timeout': opts.socket_timeout,
'bidi_workaround': opts.bidi_workaround,
'debug_printtraffic': opts.debug_printtraffic,
'prefer_ffmpeg': opts.prefer_ffmpeg,
'include_ads': opts.include_ads,
'default_search': opts.default_search,
'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
'encoding': opts.encoding,
'extract_flat': opts.extract_flat,
'mark_watched': opts.mark_watched,
'merge_output_format': opts.merge_output_format,
'postprocessors': postprocessors,
'fixup': opts.fixup,
'source_address': opts.source_address,
'call_home': opts.call_home,
'sleep_interval': opts.sleep_interval,
'max_sleep_interval': opts.max_sleep_interval,
'list_thumbnails': opts.list_thumbnails,
'playlist_items': opts.playlist_items,
'xattr_set_filesize': opts.xattr_set_filesize,
'match_filter': match_filter,
'no_color': opts.no_color,
'ffmpeg_location': opts.ffmpeg_location,
'hls_prefer_native': opts.hls_prefer_native,
'hls_use_mpegts': opts.hls_use_mpegts,
'external_downloader_args': external_downloader_args,
'postprocessor_args': postprocessor_args,
'cn_verification_proxy': opts.cn_verification_proxy,
'geo_verification_proxy': opts.geo_verification_proxy,
'config_location': opts.config_location,
'geo_bypass': opts.geo_bypass,
'geo_bypass_country': opts.geo_bypass_country,
'geo_bypass_ip_block': opts.geo_bypass_ip_block,
'autonumber': opts.autonumber if opts.autonumber is True else None,
'usetitle': opts.usetitle if opts.usetitle is True else None,
}
url = " "
with YoutubeDL(ydl_opts) as ydl:
url = ydl.extract_info(myurl)
return url
def process_url(self, source, global_opts):
"""Main method for processing urls
This method basically hands over the configuration to YoutubeDL and repeats
the step until every source in the configuration was read
"""
ydl = YoutubeDL()
ydl.add_default_info_extractors()
sourceUrl = source['url']
sourceDescription = source.get("description", "")
self._logsource(
"Processing source: '" + sourceDescription + "' Url: '" +
sourceUrl + "'", source)
# Merge local parameters with global ones
ydl.params = copy.copy(global_opts)
ydl.params.update(source)
prefix = ""
ydl.params['match_filter'] = (None if 'match_filter' not in ydl.params
or ydl.params['match_filter'] is None
else match_filter_func(
ydl.params['match_filter']))
# Settings by commute tube over the standard settings, respect if the config sets them differently
if 'format' not in ydl.params and 'format_limit' not in ydl.params:
ydl.params[
'format'] = "bestvideo+bestaudio/best" if 'format' not in self.config else self.config[
"format"]
if 'nooverwrites' not in ydl.params:
ydl.params['nooverwrites'] = True
if 'ignoreerrors' not in ydl.params:
ydl.params['ignoreerrors'] = True
if 'download_archive' not in ydl.params:
ydl.params['download_archive'] = self.download_archive
if 'prefix' in ydl.params:
prefix = ydl.params['prefix']
ydl.params['restrictfilenames'] = True
ydl.params['logger'] = self.ydlLog
outtmpl = self.pathToDownloadFolder + "/" + prefix + \
'%(uploader)s-%(title)s.%(ext)s'
if 'outtmpl' not in ydl.params:
ydl.params['outtmpl'] = outtmpl
elif not (ydl.params['outtmpl'].startswith(self.pathToDownloadFolder)):
self._logsource(
"Prefixing custom set outtmpl with '" +
self.pathToDownloadFolder + "/" + prefix + "'", source)
ydl.params['outtmpl'] = self.pathToDownloadFolder + "/" + prefix + \
ydl.params['outtmpl']
if self.debug:
self._logsource(
"All downloads will be simulated since this is debug mode",
source)
ydl.params['simulate'] = True
ydl.download([source['url']])
